-
Article
MEAN: An attention-based approach for 3D mesh shape classification
3D shape processing is a fundamental computer application. Specifically, 3D mesh could provide a natural and detailed way for object representation. However, due to its non-uniform and irregular data structure...
-
Article
WalkFormer: 3D mesh analysis via transformer on random walk
A 3D mesh is a popular representation of 3D shapes. For mesh analysis tasks, one typical method is to map 3D mesh data into 1D sequence data with random walk sampling. However, existing random walk-based appro...
-
Chapter and Conference Paper
CLF-Net: A Few-Shot Cross-Language Font Generation Method
Designing a font library takes a lot of time and effort. Few-shot font generation aims to generate a new font library by referring to only a few character samples. Accordingly, it significantly reduces labor c...
-
Article
Hybrid feature constraint with clustering for unsupervised person re-identification
Unsupervised person re-identification (Re-ID) has better scalability and usability in real-world deployments due to the lack of annotations, which is more challenging than supervised methods. State-of-the-art ...
-
Article
Open AccessNormal vibration distribution search-based differential evolution algorithm for multimodal biomedical image registration
In linear registration, a floating image is spatially aligned with a reference image after performing a series of linear metric transformations. Additionally, linear registration is mainly considered a preproc...
-
Article
Attention deep residual networks for MR image analysis
Prostate diseases often occur in men. For further clinical treatment and diagnosis, we need to do accurate segmentation on prostate. There are already many methods that concentrate on solving the problem of au...
-
Article
DRDDN: dense residual and dilated dehazing network
Recently, deep convolutional neural networks (CNNs) have made great achievements in image restoration. However, there exists a large space to improve the performance of CNN-based dehazing model. In this paper,...
-
Article
A novel privacy-preserving outsourcing computation scheme for Canny edge detection
With the advancement of cloud computing technology, cloud servers are utilized to process large-scale data, especially multimedia data. However, concerns about leakage of private information prevent cloud comp...
-
Chapter and Conference Paper
MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for...
-
Article
A multi-phase blending method with incremental intensity for training detection networks
Object detection is an important topic for visual data processing in the visual computing area. Although a number of approaches have been studied, it still remains a challenge. There is a suitable way to promo...
-
Article
Open AccessWeight asynchronous update: Improving the diversity of filters in a deep convolutional network
Deep convolutional networks have obtained remarkable achievements on various visual tasks due to their strong ability to learn a variety of features. A well-trained deep convolutional network can be compressed...
-
Article
DRCDN: learning deep residual convolutional dehazing networks
Single image dehazing, which is the process of removing haze from a single input image, is an important task in computer vision. This task is extremely challenging because it is massively ill-posed. In this pa...
-
Article
Photo-realistic dehazing via contextual generative adversarial networks
Single image dehazing is a challenging task due to its ambiguous nature. In this paper we present a new model based on generative adversarial networks (GANs) for single image dehazing, called as dehazing GAN. ...
-
Article
Part-based visual tracking with spatially regularized correlation filters
Discriminative Correlation Filters (DCFs) have demonstrated excellent performance in visual object tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifie...
-
Article
Joint learning of image detail and transmission map for single image dehazing
Single image haze removal is an important task in computer vision. However, haze removal is an extremely challenging problem due to its massively ill-posed, which is that at each pixel we must estimate the tra...
-
Chapter and Conference Paper
Single Image Dehazing Using Deep Convolution Neural Networks
Haze removal is urgently desired in multi-media system. A deep learning-based method, called dehazingCNN, is proposed to estimate an approximate clear image. The proposed learning model is different from tradi...
-
Chapter and Conference Paper
Selective Image Matting with Scalable Variance and Model Rectification
Bayesian Matting has four limitations. Firstly, Bayesian matting makes strong assumption that the texture distribution of nature image satisfies Gaussian distribution with fixed variance. This assumption will ...
-
Chapter and Conference Paper
A Fast and Secure Transmission Method Based on Optocoupler for Mobile Storage
This paper presents a one-way data transmission method in order to ensure the safety of data transmission from mobile storage to secure PC. First, an optocoupler is used to achieve the one-way transmission of ...
-
Article
Performance-based control interfaces using mixture of factor analyzers
This paper introduces an approach to performance animation that employs a small number of inertial measurement sensors to create an easy-to-use system for an interactive control of a full-body human character....